{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KFFPJ34VGKLCCNECMFDUAIWH6N","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"fa3177cbdd405ee8a3df7529dbf7acdf2d9003d6ef0ca5488abad9ec7e786ce5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-18T15:41:15Z","title_canon_sha256":"713bbc6f1861b60746bce8f416f7f68ca34ec21c709000322c4e8cc276226e36"},"schema_version":"1.0","source":{"id":"1911.07712","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.07712","created_at":"2026-07-05T00:20:07Z"},{"alias_kind":"arxiv_version","alias_value":"1911.07712v1","created_at":"2026-07-05T00:20:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.07712","created_at":"2026-07-05T00:20:07Z"},{"alias_kind":"pith_short_12","alias_value":"KFFPJ34VGKLC","created_at":"2026-07-05T00:20:07Z"},{"alias_kind":"pith_short_16","alias_value":"KFFPJ34VGKLCCNEC","created_at":"2026-07-05T00:20:07Z"},{"alias_kind":"pith_short_8","alias_value":"KFFPJ34V","created_at":"2026-07-05T00:20:07Z"}],"graph_snapshots":[{"event_id":"sha256:c922d1fa22581f0d55261893569924e879ca8ed88945110c610261ec10affb63","target":"graph","created_at":"2026-07-05T00:20:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1911.07712/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing value-factorized based Multi-Agent deep Reinforce-ment Learning (MARL) approaches are well-performing invarious multi-agent cooperative environment under thecen-tralized training and decentralized execution(CTDE) scheme,where all agents are trained together by the centralized valuenetwork and each agent execute its policy independently. How-ever, an issue remains open: in the centralized training process,when the environment for the team is partially observable ornon-stationary, i.e., the observation and action informationof all the agents cannot represent the global states, existingm","authors_text":"Bo An, Buhong Liu, Hanjiang Lai, Rundong Wang, Runsheng Yu, Xinrun Wang, Xinwen Hou, Zhenyu Shi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-18T15:41:15Z","title":"Inducing Cooperation via Team Regret Minimization based Multi-Agent Deep Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.07712","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f82d74ef61c8faee7f536b076fe118a497131d38f5fc49cd4e75220b670081cc","target":"record","created_at":"2026-07-05T00:20:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"fa3177cbdd405ee8a3df7529dbf7acdf2d9003d6ef0ca5488abad9ec7e786ce5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-11-18T15:41:15Z","title_canon_sha256":"713bbc6f1861b60746bce8f416f7f68ca34ec21c709000322c4e8cc276226e36"},"schema_version":"1.0","source":{"id":"1911.07712","kind":"arxiv","version":1}},"canonical_sha256":"514af4ef95329621348261474022c7f36d33851658bd36af6669875d55cd604e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"514af4ef95329621348261474022c7f36d33851658bd36af6669875d55cd604e","first_computed_at":"2026-07-05T00:20:07.121878Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:20:07.121878Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FTufvEZlWMX/i+g6OqGT+HjjfF6hrcPewlljlWc9lkjHbq093Tx8lLbZvwHQ12Y6HXxm5LQSzEG5/7EmI1QPDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:20:07.122342Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.07712","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f82d74ef61c8faee7f536b076fe118a497131d38f5fc49cd4e75220b670081cc","sha256:c922d1fa22581f0d55261893569924e879ca8ed88945110c610261ec10affb63"],"state_sha256":"864d10ae67e4d2526043a14a133bdcf3e5476bd0a4c93955bb2fe9bb7569fc72"}